Unbalanced CO-Optimal Transport - CNRS - Centre national de la recherche scientifique
Communication Dans Un Congrès Année : 2023

Unbalanced CO-Optimal Transport

Résumé

Optimal transport (OT) compares probability distributions by computing a meaningful alignment between their samples. CO-optimal transport (COOT) takes this comparison further by inferring an alignment between features as well. While this approach leads to better alignments and generalizes both OT and Gromov-Wasserstein distances, we provide a theoretical result showing that it is sensitive to outliers that are omnipresent in real-world data. This prompts us to propose unbalanced COOT for which we provably show its robustness to noise in the compared datasets. To the best of our knowledge, this is the first such result for OT methods in incomparable spaces. With this result in hand, we provide empirical evidence of this robustness for the challenging tasks of heterogeneous domain adaptation with and without varying proportions of classes and simultaneous alignment of samples and features across single-cell measurements.

Dates et versions

hal-04250963 , version 1 (20-10-2023)

Identifiants

Citer

Quang Huy Tran, Hicham Janati, Nicolas Courty, Rémi Flamary, Ievgen Redko, et al.. Unbalanced CO-Optimal Transport. AAAI, Feb 2023, Washington, United States. ⟨10.1609/aaai.v37i8.26193⟩. ⟨hal-04250963⟩
50 Consultations
0 Téléchargements

Altmetric

Partager

More